An image processing device and method that enable suppression of an increase in the amount of coding of a scaling list. The image processing device sets a coefficient located at the beginning of a quantization matrix by adding a replacement difference coefficient that is a difference between a replacement coefficient used to replace a coefficient located at the beginning of the quantization matrix and the coefficient located at the beginning of the quantization matrix to the coefficient located at the beginning of the quantization matrix; up-converts the set quantization matrix; and dequantizes quantized data using an up-converted quantization matrix in which a coefficient located at the beginning of the up-converted quantization matrix has been replaced with the replacement coefficient. The device and method can be applied to an image processing device.

An image decoding method performed by a decoding device according to the present document comprises the steps of: obtaining CU chroma QP offset-related information for a current chroma block on the basis of the size and tree type of the current chroma block; deriving a chroma QP for the current chroma block on the basis of the CU chroma QP offset-related information; deriving residual samples for the current chroma block on the basis of the chroma QP; and generating a reconstructed picture on the basis of the residual samples, wherein the CU chroma QP offset-related information includes a CU chroma QP offset flag and a CU chroma QP offset index for the current chroma block.

Method, apparatus, and non-transitory storage medium for end-to-end neural image compression using non-linear quantization with substitution, including receiving one or more input images, generating a substitute image associated with the input image based on the input image using a neural network based substitute feature generator, compressing the substitute image, quantizing the compressed substitute image to obtain a quantized representation of the input image with higher compression performance by using a non-linear quantizer, and entropy encoding the quantized substitute image using a neural network based encoder to generate a compressed representation of the quantized representation.

The coding of a media signal is rendered more efficient by describing the media signal using a sequence of samples and sequentially encoding this sequence by selecting, for a current sample, a set of quantization levels out of a plurality of quantization level sets depending on indices encoded into the data stream for previous samples of the sequence of samples, quantizing the current sample onto one level of the set of quantization levels, and encoding a quantization index to the one level for the current sample into the data stream. In other words, scalar quantization of the individual samples of the sequence of samples is used, but it is rendered dependent on quantization indices encoded into the data stream for previous samples of the sequence of samples. By this measure, it is possible to “construe” a grid of quantization points in the multi-dimensional space across which all possible settings of the sequence of samples are spread, onto which values of the samples are quantized according to the sequence of quantization indices coded into the data stream. This grid, in turn, reduces, statistically, a mean quantization error.

The coding of a media signal is rendered more efficient by describing the media signal using a sequence of samples and sequentially encoding this sequence by selecting, for a current sample, a set of quantization levels out of a plurality of quantization level sets depending on indices encoded into the data stream for previous samples of the sequence of samples, quantizing the current sample onto one level of the set of quantization levels, and encoding a quantization index to the one level for the current sample into the data stream. In other words, scalar quantization of the individual samples of the sequence of samples is used, but it is rendered dependent on quantization indices encoded into the data stream for previous samples of the sequence of samples. By this measure, it is possible to “construe” a grid of quantization points in the multi-dimensional space across which all possible settings of the sequence of samples are spread, onto which values of the samples are quantized according to the sequence of quantization indices coded into the data stream. This grid, in turn, reduces, statistically, a mean quantization error.

Techniques and tools for encoding enhancement layer video with quantization that varies spatially and/or between color channels are presented, along with corresponding decoding techniques and tools. For example, an encoding tool determines whether quantization varies spatially over a picture, and the tool also determines whether quantization varies between color channels in the picture. The tool signals quantization parameters for macroblocks in the picture in an encoded bit stream. In some implementations, to signal the quantization parameters, the tool predicts the quantization parameters, and the quantization parameters are signaled with reference to the predicted quantization parameters. A decoding tool receives the encoded bit stream, predicts the quantization parameters, and uses the signaled information to determine the quantization parameters for the macroblocks of the enhancement layer video. The decoding tool performs inverse quantization that can vary spatially and/or between color channels.

Techniques and tools for encoding enhancement layer video with quantization that varies spatially and/or between color channels are presented, along with corresponding decoding techniques and tools. For example, an encoding tool determines whether quantization varies spatially over a picture, and the tool also determines whether quantization varies between color channels in the picture. The tool signals quantization parameters for macroblocks in the picture in an encoded bit stream. In some implementations, to signal the quantization parameters, the tool predicts the quantization parameters, and the quantization parameters are signaled with reference to the predicted quantization parameters. A decoding tool receives the encoded bit stream, predicts the quantization parameters, and uses the signaled information to determine the quantization parameters for the macroblocks of the enhancement layer video. The decoding tool performs inverse quantization that can vary spatially and/or between color channels.

Methods for management of encoding complexity for image and video encoding, for example for algorithms belonging to the JPEG 2000 family of standards, where the encoding process targets a given compressed size (i.e. a total coded length) for the image or for each frame of a video sequence. Described are a set of methods for complexity constrained encoding of HTJ2K code-streams, involving collection of local or global statistics for each sub-band (not for each code-block), generation of forecasts for the statistics of sub-band samples that have not yet been produced by spatial transformation and quantization processes, and the use of this information to generate a global quantization parameter, from which the coarsest bit-plane to generate in each code-block can be deduced. Coded length estimates can be generated in a manner that enables latency and memory to be separately optimized against encoded image quality, while maintaining low computational complexity.

Provided is a signal reconstruction method executed by a signal reconstruction apparatus including a processor and a memory that stores a codec. The signal reconstruction method includes reconstructing an input signal according to a desired purpose, and in the reconstructing, a likelihood of the input signal being a predetermined type of signal is considered by executing coding on a processing result of the input signal, based on the codec previously determined according to a type of the input signal.

Provided is a signal reconstruction method executed by a signal reconstruction apparatus including a processor and a memory that stores a codec. The signal reconstruction method includes reconstructing an input signal according to a desired purpose, and in the reconstructing, a likelihood of the input signal being a predetermined type of signal is considered by executing coding on a processing result of the input signal, based on the codec previously determined according to a type of the input signal.